EXPERIMENTAL INVESTIGATIONS FOR QUALITY ENHANCEMENT OF DENTAL PROSTHESIS DESIGNED USING 3D SCANNING AND RESIN PRINTING TECHNIQUE

Abstract

Customized fabrication and decreased intervention are two benefits of 3D printed occlusal dental splints; however, differences in printing parameters, resin properties, dimensional accuracy, manufacturing expenses, and design time might restrict their regular clinical utility. This research is about testing, via experimentation, a machine learning driven optimization strategy that could improve the accuracy and cost-effectiveness of 3D printed occlusal dental splints. The proposed method is based on a fusion of 3D scanning, computer-aided design, 3D printing using resin-based materials, and machine learning to determine the best printing conditions that not only lead to better dimensional accuracy, but also to reduced costs arising from material and fabrication time.

When appropriate, the fabrication time, production cost, dimensional measurements, mechanical and surface evaluations are used to examine experimental samples; traditional or non-optimized fabrication is utilized for comparison. According to the source literature personalisation and improved manufacturing efficiency are possible with digital workflows; the orientation of the build, the thickness of the layers, the printing speed, the composition of the resin, the calibration of the printer, and the post-curing conditions all have a significant influence on the dimensional and mechanical performance. As no validated statistical comparison or machine-learning result is available in the experimental source, it is not allowed to claim increase in performance at the specimen level without an experimental result. The objective of the study is to develop optimization framework on the basis of science principles supporting production of splint items with a high degree of accuracy for maximum quality, cost competitiveness and applicability in clinical practice. In the future, clinical trials, standardized protocols and datasets would be used to validate the model.